
from sklearn.datasets import load_files       
from keras.utils import np_utils
import numpy as np
from glob import glob

# define function to load train, test, and validation datasets
def load_dataset(path):
    data = load_files(path)
    dog_files = np.array(data['filenames'])
    dog_targets = np_utils.to_categorical(np.array(data['target']), 133)
    return dog_files, dog_targets

# load train, test, and validation datasets
train_files, train_targets = load_dataset('dogImages/train')
valid_files, valid_targets = load_dataset('dogImages/valid')
test_files, test_targets = load_dataset('dogImages/test')

# load list of dog names
dog_names = [item[20:-1] for item in sorted(glob("dogImages/train/*/"))]

# print statistics about the dataset
print('There are %d total dog categories.' % len(dog_names))
print('There are %s total dog images.\n' % len(np.hstack([train_files, valid_files, test_files])))
print('There are %d training dog images.' % len(train_files))
print('There are %d validation dog images.' % len(valid_files))
print('There are %d test dog images.'% len(test_files))

There are 133 total dog categories.
There are 8351 total dog images.

There are 6680 training dog images.
There are 835 validation dog images.
There are 836 test dog images.


# Since I can't reference pictures directly from the udacity urls,
# we are gonna use a helper function to embed images properly using html.

from IPython.display import Image, HTML, display
import base64

def to_dog_labels(arr):
    return dog_names[arr.argmax()].split("/")[-1]


def img_to_html(img_path, figcaption="", height="150px"):
    '''convert image to data in base64
    then construct html img block
    '''

    figure_html = '''
    <figure style= '{figstyle}'>
      <img style='{imgstyle}' src='{imgsrc}'/>
      <figcaption style='font-size:80%; text-align:center'>{figcaption}</figcaption>
    </figure>
    '''

    figstyle = "margin: 10px; float: left; border: 3px solid black;"
    imgstyle = "height:{}; padding: 5px;".format(height)


    img_base64 = str(base64.b64encode(Image(img_path).data))[2:]
    
    html = figure_html.format(
        figstyle = figstyle,
        imgstyle = imgstyle,
        imgsrc = 'data:image/jpeg;base64,' + img_base64,
        figcaption = figcaption
    )
    
    return html


def gallery(files, labels="", height="150px"): 
    '''uses html display to show image files inline in jupyter'''
    images_list = ""
    if not labels : 
        for file in files:
            images_list += (img_to_html(file, figcaption="", height=height))
    else : 
        for file, label in zip(files, labels):
            images_list += (img_to_html(file, figcaption=label, height=height))

    display(HTML(images_list))


gallery(train_files[:18], [to_dog_labels(t) for t in train_targets[:18]])


import random
random.seed(8675319)

# load filenames in shuffled human dataset
human_files = np.array(glob("lfw/*/*"))
random.shuffle(human_files)

# print statistics about the dataset
print('There are %d total human images.' % len(human_files))

There are 13233 total human images.


import cv2                
import matplotlib.pyplot as plt                        
%matplotlib inline                               

# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')

# load color (BGR) image
img = cv2.imread(human_files[3])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# find faces in image
faces = face_cascade.detectMultiScale(gray)

# print number of faces detected in the image
print('Number of faces detected:', len(faces))

# get bounding box for each detected face
for (x,y,w,h) in faces:
    # add bounding box to color image
    cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
    
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()

Number of faces detected: 1


# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray)
    return len(faces) > 0


human_files_short = human_files[:100]
dog_files_short = train_files[:100]
# Do NOT modify the code above this line.

## TODO: Test the performance of the face_detector algorithm 
## on the images in human_files_short and dog_files_short.

# small helper function
def faces_positive(img_list):
    '''implements face_detector over an image list.
    Returns the sum of positive outcomes in a list.
    '''
    results = []
    
    for img in img_list:
        results.append(face_detector(img))
    
    return np.sum(results)
    

print("What percentage of the first 100 images in human_files have a detected human face?")
print((faces_positive(human_files_short)/len(human_files_short))*100)

print("What percentage of the first 100 images in dog_files have a detected human face?")
print((faces_positive(dog_files_short)/len(dog_files_short))*100)

What percentage of the first 100 images in human_files have a detected human face?
97.0
What percentage of the first 100 images in dog_files have a detected human face?
12.0


## (Optional) TODO: Report the performance of another  
## face detection algorithm on the LFW dataset
### Feel free to use as many code cells as needed.


import dlib
from imutils import face_utils

# Original human face detection Haar-like 
def face_detector(img_path):
    """Returns True if a face is found."""
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray)
    return len(faces) > 0 


# Alternative algorithm # 1 
# Histogram of Oriented Gradients (HOG) in Dlib 
# https://lear.inrialpes.fr/people/triggs/pubs/Dalal-cvpr05.pdf

def hog_face_detector(img_path):
    """Returns True if a face is found."""
    face_hog = dlib.get_frontal_face_detector()
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    rects = face_hog(gray, 1)
    return len(rects) > 0


# Alternative algorithm # 2
# Convolutional Neural Network in Dlib
# model file obtained here: http://dlib.net/files/mmod_human_face_detector.dat.bz2

def cnn_face_detector(img_path):
    """Returns True if a face is found."""
    face_cnn = dlib.cnn_face_detection_model_v1("mmod/mmod_human_face_detector.dat")
    img = cv2.imread(img_path)

    # Resize the image to attain reasonable speed:
    # img = cv2.resize(img, (0, 0), fx=0.5, fy=0.5)
    
    rects = face_cnn(img, 1)
    return len(rects) > 0


# Creating a loop function to compare Haar-like vs 2 alternative models.

from tqdm import tqdm

def compare_human_detectors(test_images, detectors):
    '''Takes a list of images paths and test them against a list of detectors,
    comparing and printig the final detection rate. 
    Returns a list of dictionaries containing results.
    Note : detectors must be functions returning a boolean.
    '''
    results = []
    size = len(test_images)

    print("Begin test of sample of ", test_images.shape[0])

    for img in tqdm(test_images):

        d = {
            "img_path":None,
            "results" : [],
        }

        d["img_path"] = img

        # Test against each detector

        for i, detector in enumerate(detectors): 
            d["results"].append(detector(img))

        results.append(d)
        # bar1.update(int(1))

    # Print detection rate

    for i in range(len(detectors)):
        detection_rate = np.sum([x["results"][i] for x in results]) / size * 100
        print("  detector # {} : {:.2f} %".format(i+1, detection_rate))

    return results


# Run test 1: detect humans in humans
# ⚠️ this may take a while because of CNN-MMOD's computations times

detectors = [
    face_detector, 
    hog_face_detector, 
    cnn_face_detector
    ]

print("Part 1: humans in humans")
hh = compare_human_detectors(human_files_short, detectors=detectors)

Part 1: humans in humans
Begin test of sample of  100

100%|██████████| 100/100 [05:38<00:00,  3.39s/it]

  detector # 1 : 97.00 %
  detector # 2 : 99.00 %
  detector # 3 : 100.00 %


# Run test 1:  humans in dog images
# ⚠️ this may take a while because of CNN-MMOD's computations times

print("Part 2: humans in dogs")
hd = compare_human_detectors(dog_files_short, detectors=detectors)

Part 2: humans in dogs
Begin test of sample of  100

100%|██████████| 100/100 [34:26<00:00, 20.66s/it]

  detector # 1 : 12.00 %
  detector # 2 : 8.00 %
  detector # 3 : 2.00 %


#that took a while. I'm gonna save those results
import json

# with open("hh_results.json", "w") as jp:
#     json.dump(hh, jp) 

# with open("hd_results.json", "w") as jp:
#     json.dump(hd, jp) 

# relading

# Opening JSON file
with open('hh_results.json') as json_file:
    hh = json.load(json_file)
with open('hd_results.json') as json_file:
    hd = json.load(json_file)


# take a look at those inconsistencies in human detection

arr = np.sum([i["results"] for i in hh], axis=1)
ixs = np.where(arr<3)

print("Showing images with detection discrepancies among models")

images = [hh[ix]["img_path"] for ix in ixs[0]]
labels = [hh[ix]["img_path"].split("\\")[-1] + "</br>" + str(hh[ix]["results"]) for ix in ixs[0]]

gallery(images, labels)

Showing images with detection discrepancies among models


# take a look at those inconsistencies in human in dogs detection

arr = np.sum([i["results"] for i in hd], axis=1)
ixs = np.where(arr>0)

print("Showing images with detection discrepancies among models, for the dogs sample")

images = [hd[ix]["img_path"] for ix in ixs[0]]
labels = [hd[ix]["img_path"].split("\\")[-1] + "</br>" + str(hd[ix]["results"]) for ix in ixs[0]]

gallery(images, labels)

Showing images with detection discrepancies among models, for the dogs sample


from io import BytesIO
import base64
import PIL
import imutils


# drawing boxes for better inspection

def draw_bow(faces, image_np, text, color):
    '''draw boxes using faces coordinates and annotates text in image'''

    for (x,y,w,h) in faces:
        cv2.rectangle(image_np,(x,y),(x+w,y+h), color,2)
        cv2.putText(image_np, text, (x,y-3), fontFace = cv2.FONT_HERSHEY_PLAIN, fontScale = 1, color = color)

def bboxes(img_path):
        '''implement various face detection models and draw boxes.
        Returns image in a 4-dimensions array (numpy.array).'''
        
        img = cv2.imread(img_path)

        # resize very large images
        if img.shape[0] > 700:
            img = imutils.resize(img, width=700)

        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

        # Haar-like
        face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')
        faces = face_cascade.detectMultiScale(gray)
        if len(faces) > 0: 
            draw_bow(faces, img, "haar", (255,0,255))
        
        # HoG
        face_hog = dlib.get_frontal_face_detector()
        rects = face_hog(gray, 1)
        if rects : 
            faces = []
            for d in rects :
                faces.append(face_utils.rect_to_bb(d))
            faces = np.array(faces)
            draw_bow(faces, img, "hog-svm", (255,255,0))
            
        # CNN
        face_cnn = dlib.cnn_face_detection_model_v1("mmod/mmod_human_face_detector.dat")
        rects = face_cnn(img, 1)
        if rects:
            faces = np.array([face_utils.rect_to_bb(rects[0].rect)])
            draw_bow(faces, img, "cnn", (0,255,255))


        return cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        
        
def to_b64(image_array):
    '''transforms nd.array image into b64 string'''

    pil_img = PIL.Image.fromarray(image_array)
    buff = BytesIO()
    pil_img.save(buff, format="PNG")
    b64str = base64.b64encode(buff.getvalue()).decode("utf-8")

    return b64str


# Run to see some false positives examples.
# ⚠️ this may take a while because of CNN-MMOD's computations times

images_html = ""

for img_path in tqdm(images):

    image_with_bboxes = bboxes(img_path)
    figure_html= "<figure style='height: 300px; margin: 20px 10px; float: left'><img src='{imgsrc}'/></figure>"
    html = figure_html.format(
        imgsrc = 'data:image/jpeg;base64,' + to_b64(image_with_bboxes),
    )
    images_html += html


display(HTML(images_html))

100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [03:45<00:00, 13.26s/it]


from keras.applications.resnet import ResNet50

# define ResNet50 model
ResNet50_model = ResNet50(weights='imagenet')


import keras
# from tqdm import tqdm

def path_to_tensor(img_path):
    # loads RGB image as PIL.Image.Image type
    img = keras.utils.load_img(img_path, target_size=(224, 224))
    # convert PIL.Image.Image type to 3D tensor with shape (224, 224, 3)
    x = keras.utils.img_to_array(img)
    # convert 3D tensor to 4D tensor with shape (1, 224, 224, 3) and return 4D tensor
    return np.expand_dims(x, axis=0)

def paths_to_tensor(img_paths):
    list_of_tensors = [path_to_tensor(img_path) for img_path in tqdm(img_paths)]

    return np.vstack(list_of_tensors)


path_to_tensor(human_files[0]).shape

(1, 224, 224, 3)


from keras.applications.resnet import ResNet50, preprocess_input, decode_predictions

def ResNet50_predict_labels(img_path):
    # returns prediction vector for image located at img_path
    img = preprocess_input(path_to_tensor(img_path))
    return np.argmax(ResNet50_model.predict(img, verbose=0))    # added verbose=0 for silent


### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
    prediction = ResNet50_predict_labels(img_path)
    return ((prediction <= 268) & (prediction >= 151))


### TODO: Test the performance of the dog_detector function
### on the images in human_files_short and dog_files_short.

# Loop and store results in list
print("running assessment(s)")

results_dogs_in_humans =[]
results_dogs_in_dogs = []

for img in tqdm(human_files_short): 
    results_dogs_in_humans.append(dog_detector(img))

for img in tqdm(dog_files_short): 
    results_dogs_in_dogs.append(dog_detector(img))

# Print results
print("Percentage of dog-detection in human_files_short :")
print((np.sum(results_dogs_in_humans)/len(human_files_short))*100)

print("Percentage of dog-detection in dog_files_short :")
print((np.sum(results_dogs_in_dogs)/len(dog_files_short))*100)

running assessment(s)

100%|████████████████████████████████████████████████████████████████████████████████| 100/100 [00:10<00:00,  9.15it/s]
100%|████████████████████████████████████████████████████████████████████████████████| 100/100 [00:11<00:00,  8.96it/s]

Percentage of dog-detection in human_files_short :
0.0
Percentage of dog-detection in dog_files_short :
100.0


from PIL import ImageFile                            
ImageFile.LOAD_TRUNCATED_IMAGES = True
from tqdm import tqdm

# pre-process the data for Keras
train_tensors = paths_to_tensor(train_files).astype('float32')/255
valid_tensors = paths_to_tensor(valid_files).astype('float32')/255
test_tensors = paths_to_tensor(test_files).astype('float32')/255

100%|█████████████████████████████████████████████████████████████████████████████| 6680/6680 [00:31<00:00, 212.98it/s]
100%|███████████████████████████████████████████████████████████████████████████████| 835/835 [00:03<00:00, 224.13it/s]
100%|███████████████████████████████████████████████████████████████████████████████| 836/836 [00:03<00:00, 231.37it/s]


import keras
from tensorflow.keras import layers

### TODO: Define your architecture.

inputs = keras.Input(shape=((224, 224, 3)))

# best one overall
model = keras.Sequential(
    [
        inputs,
                
        layers.Conv2D(16, kernel_size=3, activation='relu'),
        layers.MaxPooling2D(pool_size=3, strides=2),
        
        layers.Conv2D(32, kernel_size=3, activation='relu', padding="same"),
        layers.MaxPooling2D(pool_size=3, strides=2),
        
        layers.Conv2D(16, kernel_size=3, activation='relu', padding="same"),
        layers.MaxPooling2D(pool_size=3, strides=2),
        
        layers.GlobalAveragePooling2D(),
        layers.Dense(units=133, activation="softmax")    #sigmoid or softmax are suited for multiple classes
    ]
)


model.summary(line_length=90)

Model: "sequential_1"
__________________________________________________________________________________________
 Layer (type)                           Output Shape                        Param #       
==========================================================================================
 conv2d (Conv2D)                        (None, 222, 222, 16)                448           
                                                                                          
 max_pooling2d (MaxPooling2D)           (None, 110, 110, 16)                0             
                                                                                          
 conv2d_1 (Conv2D)                      (None, 110, 110, 32)                4640          
                                                                                          
 max_pooling2d_1 (MaxPooling2D)         (None, 54, 54, 32)                  0             
                                                                                          
 conv2d_2 (Conv2D)                      (None, 54, 54, 16)                  4624          
                                                                                          
 max_pooling2d_2 (MaxPooling2D)         (None, 26, 26, 16)                  0             
                                                                                          
 global_average_pooling2d (GlobalAverag  (None, 16)                         0             
 ePooling2D)                                                                              
                                                                                          
 dense (Dense)                          (None, 133)                         2261          
                                                                                          
==========================================================================================
Total params: 11,973
Trainable params: 11,973
Non-trainable params: 0
__________________________________________________________________________________________


model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])


import datetime

### TODO: specify the number of epochs that you would like to use to train the model.

epochs = 50

### Do NOT modify the code below this line.

log_dir = "logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")

callbacks = [
    keras.callbacks.ModelCheckpoint(
        filepath='saved_models/weights.best.from_scratch.hdf5',
        verbose=1,
        save_best_only=True
    ),
    keras.callbacks.TensorBoard(
        log_dir = log_dir
    )
]

hist = model.fit(
    train_tensors, 
    train_targets, 
    validation_data=(valid_tensors, valid_targets),
    epochs=epochs, 
    batch_size=20, 
    callbacks=callbacks, 
    verbose=1
)

Epoch 1/50
334/334 [==============================] - ETA: 0s - loss: 4.8816 - accuracy: 0.0103
Epoch 1: val_loss improved from inf to 4.86501, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 30s 87ms/step - loss: 4.8816 - accuracy: 0.0103 - val_loss: 4.8650 - val_accuracy: 0.0180
Epoch 2/50
334/334 [==============================] - ETA: 0s - loss: 4.8433 - accuracy: 0.0129
Epoch 2: val_loss improved from 4.86501 to 4.82942, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 35s 105ms/step - loss: 4.8433 - accuracy: 0.0129 - val_loss: 4.8294 - val_accuracy: 0.0204
Epoch 3/50
334/334 [==============================] - ETA: 0s - loss: 4.8010 - accuracy: 0.0153
Epoch 3: val_loss improved from 4.82942 to 4.78743, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 32s 95ms/step - loss: 4.8010 - accuracy: 0.0153 - val_loss: 4.7874 - val_accuracy: 0.0287
Epoch 4/50
334/334 [==============================] - ETA: 0s - loss: 4.7560 - accuracy: 0.0187
Epoch 4: val_loss improved from 4.78743 to 4.75643, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 32s 97ms/step - loss: 4.7560 - accuracy: 0.0187 - val_loss: 4.7564 - val_accuracy: 0.0216
Epoch 5/50
334/334 [==============================] - ETA: 0s - loss: 4.7231 - accuracy: 0.0234
Epoch 5: val_loss improved from 4.75643 to 4.73187, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 33s 97ms/step - loss: 4.7231 - accuracy: 0.0234 - val_loss: 4.7319 - val_accuracy: 0.0216
Epoch 6/50
334/334 [==============================] - ETA: 0s - loss: 4.6935 - accuracy: 0.0257
Epoch 6: val_loss improved from 4.73187 to 4.71594, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 28s 82ms/step - loss: 4.6935 - accuracy: 0.0257 - val_loss: 4.7159 - val_accuracy: 0.0228
Epoch 7/50
334/334 [==============================] - ETA: 0s - loss: 4.6637 - accuracy: 0.0295
Epoch 7: val_loss improved from 4.71594 to 4.69795, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 27s 82ms/step - loss: 4.6637 - accuracy: 0.0295 - val_loss: 4.6979 - val_accuracy: 0.0251
Epoch 8/50
334/334 [==============================] - ETA: 0s - loss: 4.6344 - accuracy: 0.0352
Epoch 8: val_loss improved from 4.69795 to 4.69542, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 29s 86ms/step - loss: 4.6344 - accuracy: 0.0352 - val_loss: 4.6954 - val_accuracy: 0.0228
Epoch 9/50
334/334 [==============================] - ETA: 0s - loss: 4.6063 - accuracy: 0.0388
Epoch 9: val_loss improved from 4.69542 to 4.66292, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 78ms/step - loss: 4.6063 - accuracy: 0.0388 - val_loss: 4.6629 - val_accuracy: 0.0323
Epoch 10/50
334/334 [==============================] - ETA: 0s - loss: 4.5766 - accuracy: 0.0388
Epoch 10: val_loss improved from 4.66292 to 4.64510, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 78ms/step - loss: 4.5766 - accuracy: 0.0388 - val_loss: 4.6451 - val_accuracy: 0.0299
Epoch 11/50
334/334 [==============================] - ETA: 0s - loss: 4.5453 - accuracy: 0.0442
Epoch 11: val_loss improved from 4.64510 to 4.63822, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 30s 89ms/step - loss: 4.5453 - accuracy: 0.0442 - val_loss: 4.6382 - val_accuracy: 0.0395
Epoch 12/50
334/334 [==============================] - ETA: 0s - loss: 4.5211 - accuracy: 0.0433
Epoch 12: val_loss improved from 4.63822 to 4.59973, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 29s 87ms/step - loss: 4.5211 - accuracy: 0.0433 - val_loss: 4.5997 - val_accuracy: 0.0395
Epoch 13/50
334/334 [==============================] - ETA: 0s - loss: 4.4861 - accuracy: 0.0455
Epoch 13: val_loss improved from 4.59973 to 4.57351, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 77ms/step - loss: 4.4861 - accuracy: 0.0455 - val_loss: 4.5735 - val_accuracy: 0.0359
Epoch 14/50
334/334 [==============================] - ETA: 0s - loss: 4.4599 - accuracy: 0.0540
Epoch 14: val_loss improved from 4.57351 to 4.53750, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 76ms/step - loss: 4.4599 - accuracy: 0.0540 - val_loss: 4.5375 - val_accuracy: 0.0335
Epoch 15/50
334/334 [==============================] - ETA: 0s - loss: 4.4230 - accuracy: 0.0557
Epoch 15: val_loss did not improve from 4.53750
334/334 [==============================] - 31s 93ms/step - loss: 4.4230 - accuracy: 0.0557 - val_loss: 4.6045 - val_accuracy: 0.0287
Epoch 16/50
334/334 [==============================] - ETA: 0s - loss: 4.3931 - accuracy: 0.0612
Epoch 16: val_loss improved from 4.53750 to 4.52353, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 78ms/step - loss: 4.3931 - accuracy: 0.0612 - val_loss: 4.5235 - val_accuracy: 0.0263
Epoch 17/50
334/334 [==============================] - ETA: 0s - loss: 4.3615 - accuracy: 0.0594
Epoch 17: val_loss improved from 4.52353 to 4.48902, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 78ms/step - loss: 4.3615 - accuracy: 0.0594 - val_loss: 4.4890 - val_accuracy: 0.0431
Epoch 18/50
334/334 [==============================] - ETA: 0s - loss: 4.3260 - accuracy: 0.0653
Epoch 18: val_loss improved from 4.48902 to 4.42274, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 79ms/step - loss: 4.3260 - accuracy: 0.0653 - val_loss: 4.4227 - val_accuracy: 0.0407
Epoch 19/50
334/334 [==============================] - ETA: 0s - loss: 4.2923 - accuracy: 0.0671
Epoch 19: val_loss did not improve from 4.42274
334/334 [==============================] - 26s 78ms/step - loss: 4.2923 - accuracy: 0.0671 - val_loss: 4.4260 - val_accuracy: 0.0527
Epoch 20/50
334/334 [==============================] - ETA: 0s - loss: 4.2660 - accuracy: 0.0754
Epoch 20: val_loss improved from 4.42274 to 4.35517, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 28s 84ms/step - loss: 4.2660 - accuracy: 0.0754 - val_loss: 4.3552 - val_accuracy: 0.0491
Epoch 21/50
334/334 [==============================] - ETA: 0s - loss: 4.2356 - accuracy: 0.0726
Epoch 21: val_loss did not improve from 4.35517
334/334 [==============================] - 27s 81ms/step - loss: 4.2356 - accuracy: 0.0726 - val_loss: 4.3598 - val_accuracy: 0.0479
Epoch 22/50
334/334 [==============================] - ETA: 0s - loss: 4.2083 - accuracy: 0.0754
Epoch 22: val_loss did not improve from 4.35517
334/334 [==============================] - 31s 92ms/step - loss: 4.2083 - accuracy: 0.0754 - val_loss: 4.3603 - val_accuracy: 0.0575
Epoch 23/50
334/334 [==============================] - ETA: 0s - loss: 4.1877 - accuracy: 0.0756
Epoch 23: val_loss improved from 4.35517 to 4.30869, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 79ms/step - loss: 4.1877 - accuracy: 0.0756 - val_loss: 4.3087 - val_accuracy: 0.0587
Epoch 24/50
334/334 [==============================] - ETA: 0s - loss: 4.1641 - accuracy: 0.0858
Epoch 24: val_loss improved from 4.30869 to 4.30740, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 27s 81ms/step - loss: 4.1641 - accuracy: 0.0858 - val_loss: 4.3074 - val_accuracy: 0.0599
Epoch 25/50
334/334 [==============================] - ETA: 0s - loss: 4.1427 - accuracy: 0.0835
Epoch 25: val_loss improved from 4.30740 to 4.25449, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 28s 83ms/step - loss: 4.1427 - accuracy: 0.0835 - val_loss: 4.2545 - val_accuracy: 0.0587
Epoch 26/50
334/334 [==============================] - ETA: 0s - loss: 4.1206 - accuracy: 0.0871
Epoch 26: val_loss did not improve from 4.25449
334/334 [==============================] - 26s 78ms/step - loss: 4.1206 - accuracy: 0.0871 - val_loss: 4.3178 - val_accuracy: 0.0647
Epoch 27/50
334/334 [==============================] - ETA: 0s - loss: 4.0976 - accuracy: 0.0898
Epoch 27: val_loss did not improve from 4.25449
334/334 [==============================] - 28s 84ms/step - loss: 4.0976 - accuracy: 0.0898 - val_loss: 4.2963 - val_accuracy: 0.0635
Epoch 28/50
334/334 [==============================] - ETA: 0s - loss: 4.0744 - accuracy: 0.0927
Epoch 28: val_loss did not improve from 4.25449
334/334 [==============================] - 26s 77ms/step - loss: 4.0744 - accuracy: 0.0927 - val_loss: 4.2782 - val_accuracy: 0.0611
Epoch 29/50
334/334 [==============================] - ETA: 0s - loss: 4.0502 - accuracy: 0.0954
Epoch 29: val_loss improved from 4.25449 to 4.20806, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 76ms/step - loss: 4.0502 - accuracy: 0.0954 - val_loss: 4.2081 - val_accuracy: 0.0802
Epoch 30/50
334/334 [==============================] - ETA: 0s - loss: 4.0406 - accuracy: 0.0949
Epoch 30: val_loss improved from 4.20806 to 4.19541, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 77ms/step - loss: 4.0406 - accuracy: 0.0949 - val_loss: 4.1954 - val_accuracy: 0.0683
Epoch 31/50
334/334 [==============================] - ETA: 0s - loss: 4.0197 - accuracy: 0.0994
Epoch 31: val_loss did not improve from 4.19541
334/334 [==============================] - 26s 77ms/step - loss: 4.0197 - accuracy: 0.0994 - val_loss: 4.2731 - val_accuracy: 0.0623
Epoch 32/50
334/334 [==============================] - ETA: 0s - loss: 3.9935 - accuracy: 0.0996
Epoch 32: val_loss improved from 4.19541 to 4.15689, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 28s 83ms/step - loss: 3.9935 - accuracy: 0.0996 - val_loss: 4.1569 - val_accuracy: 0.0814
Epoch 33/50
334/334 [==============================] - ETA: 0s - loss: 3.9803 - accuracy: 0.1034
Epoch 33: val_loss did not improve from 4.15689
334/334 [==============================] - 33s 98ms/step - loss: 3.9803 - accuracy: 0.1034 - val_loss: 4.1690 - val_accuracy: 0.0719
Epoch 34/50
334/334 [==============================] - ETA: 0s - loss: 3.9628 - accuracy: 0.1078
Epoch 34: val_loss did not improve from 4.15689
334/334 [==============================] - 32s 95ms/step - loss: 3.9628 - accuracy: 0.1078 - val_loss: 4.1920 - val_accuracy: 0.0862
Epoch 35/50
334/334 [==============================] - ETA: 0s - loss: 3.9474 - accuracy: 0.1087
Epoch 35: val_loss improved from 4.15689 to 4.13415, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 33s 100ms/step - loss: 3.9474 - accuracy: 0.1087 - val_loss: 4.1341 - val_accuracy: 0.0683
Epoch 36/50
334/334 [==============================] - ETA: 0s - loss: 3.9332 - accuracy: 0.1091
Epoch 36: val_loss did not improve from 4.13415
334/334 [==============================] - 34s 100ms/step - loss: 3.9332 - accuracy: 0.1091 - val_loss: 4.2382 - val_accuracy: 0.0659
Epoch 37/50
334/334 [==============================] - ETA: 0s - loss: 3.9212 - accuracy: 0.1078
Epoch 37: val_loss improved from 4.13415 to 4.05745, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 78ms/step - loss: 3.9212 - accuracy: 0.1078 - val_loss: 4.0575 - val_accuracy: 0.0922
Epoch 38/50
334/334 [==============================] - ETA: 0s - loss: 3.9004 - accuracy: 0.1105
Epoch 38: val_loss did not improve from 4.05745
334/334 [==============================] - 26s 79ms/step - loss: 3.9004 - accuracy: 0.1105 - val_loss: 4.0759 - val_accuracy: 0.0826
Epoch 39/50
334/334 [==============================] - ETA: 0s - loss: 3.8902 - accuracy: 0.1183
Epoch 39: val_loss did not improve from 4.05745
334/334 [==============================] - 28s 84ms/step - loss: 3.8902 - accuracy: 0.1183 - val_loss: 4.1000 - val_accuracy: 0.0766
Epoch 40/50
334/334 [==============================] - ETA: 0s - loss: 3.8772 - accuracy: 0.1177
Epoch 40: val_loss did not improve from 4.05745
334/334 [==============================] - 26s 78ms/step - loss: 3.8772 - accuracy: 0.1177 - val_loss: 4.0726 - val_accuracy: 0.0826
Epoch 41/50
334/334 [==============================] - ETA: 0s - loss: 3.8599 - accuracy: 0.1199
Epoch 41: val_loss did not improve from 4.05745
334/334 [==============================] - 26s 79ms/step - loss: 3.8599 - accuracy: 0.1199 - val_loss: 4.1577 - val_accuracy: 0.0898
Epoch 42/50
334/334 [==============================] - ETA: 0s - loss: 3.8494 - accuracy: 0.1178
Epoch 42: val_loss improved from 4.05745 to 4.03318, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 26s 79ms/step - loss: 3.8494 - accuracy: 0.1178 - val_loss: 4.0332 - val_accuracy: 0.0874
Epoch 43/50
334/334 [==============================] - ETA: 0s - loss: 3.8385 - accuracy: 0.1244
Epoch 43: val_loss did not improve from 4.03318
334/334 [==============================] - 31s 92ms/step - loss: 3.8385 - accuracy: 0.1244 - val_loss: 4.1212 - val_accuracy: 0.0970
Epoch 44/50
334/334 [==============================] - ETA: 0s - loss: 3.8205 - accuracy: 0.1237
Epoch 44: val_loss did not improve from 4.03318
334/334 [==============================] - 26s 79ms/step - loss: 3.8205 - accuracy: 0.1237 - val_loss: 4.1646 - val_accuracy: 0.1006
Epoch 45/50
334/334 [==============================] - ETA: 0s - loss: 3.8142 - accuracy: 0.1277
Epoch 45: val_loss did not improve from 4.03318
334/334 [==============================] - 26s 78ms/step - loss: 3.8142 - accuracy: 0.1277 - val_loss: 4.0412 - val_accuracy: 0.0731
Epoch 46/50
334/334 [==============================] - ETA: 0s - loss: 3.8040 - accuracy: 0.1305
Epoch 46: val_loss did not improve from 4.03318
334/334 [==============================] - 26s 78ms/step - loss: 3.8040 - accuracy: 0.1305 - val_loss: 4.0406 - val_accuracy: 0.0910
Epoch 47/50
334/334 [==============================] - ETA: 0s - loss: 3.7957 - accuracy: 0.1271
Epoch 47: val_loss improved from 4.03318 to 3.98193, saving model to saved_models\weights.best.from_scratch.hdf5
334/334 [==============================] - 28s 84ms/step - loss: 3.7957 - accuracy: 0.1271 - val_loss: 3.9819 - val_accuracy: 0.1162
Epoch 48/50
334/334 [==============================] - ETA: 0s - loss: 3.7781 - accuracy: 0.1362
Epoch 48: val_loss did not improve from 3.98193
334/334 [==============================] - 39s 115ms/step - loss: 3.7781 - accuracy: 0.1362 - val_loss: 4.0130 - val_accuracy: 0.1030
Epoch 49/50
334/334 [==============================] - ETA: 0s - loss: 3.7635 - accuracy: 0.1356
Epoch 49: val_loss did not improve from 3.98193
334/334 [==============================] - 37s 110ms/step - loss: 3.7635 - accuracy: 0.1356 - val_loss: 4.0001 - val_accuracy: 0.1006
Epoch 50/50
334/334 [==============================] - ETA: 0s - loss: 3.7579 - accuracy: 0.1340
Epoch 50: val_loss did not improve from 3.98193
334/334 [==============================] - 28s 85ms/step - loss: 3.7579 - accuracy: 0.1340 - val_loss: 4.0088 - val_accuracy: 0.1066


def plot_loss_acc(hist, title):
    '''plot loss and accuracy of model history object (keras.model.hist)'''
    
    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 4))
    fig.suptitle(title, fontsize=16)
    
    ax1.plot(hist.history["loss"], c="teal", label="loss")
    ax1.plot(hist.history["val_loss"], c="teal", label="val_loss", ls="--")
    ax1.set_title('Loss')
    ax1.legend(loc="upper right")
    
    ax2.plot(hist.history["accuracy"], c="orange", label="accuracy")
    ax2.plot(hist.history["val_accuracy"], c="orange", label="val_accuracy", ls="--")
    ax2.set_title('Accuracy')
    ax2.legend(loc="upper left")

    plt.show()


plot_loss_acc(hist, "Dog Breed classifier training (from Scratch)")


model.load_weights('saved_models/weights.best.from_scratch.hdf5')


# get index of predicted dog breed for each image in test set
dog_breed_predictions = [np.argmax(model.predict(np.expand_dims(tensor, axis=0), verbose=0)) for tensor in tqdm(test_tensors)]

# report test accuracy
test_accuracy = 100*np.sum(np.array(dog_breed_predictions)==np.argmax(test_targets, axis=1))/len(dog_breed_predictions)
print('Test accuracy: %.4f%%' % test_accuracy)

100%|████████████████████████████████████████████████████████████████████████████████| 836/836 [00:46<00:00, 17.86it/s]

Test accuracy: 12.2010%


bottleneck_features = np.load('bottleneck_features/DogVGG16Data.npz')
train_VGG16 = bottleneck_features['train']
valid_VGG16 = bottleneck_features['valid']
test_VGG16 = bottleneck_features['test']


from keras import layers

VGG16_model = keras.Sequential()
VGG16_model.add(layers.GlobalAveragePooling2D(input_shape=train_VGG16.shape[1:]))
VGG16_model.add(layers.Dense(133, activation='softmax'))

VGG16_model.summary()

Model: "sequential_2"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 global_average_pooling2d_1   (None, 512)              0         
 (GlobalAveragePooling2D)                                        
                                                                 
 dense_1 (Dense)             (None, 133)               68229     
                                                                 
=================================================================
Total params: 68,229
Trainable params: 68,229
Non-trainable params: 0
_________________________________________________________________


VGG16_model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])


checkpointer = keras.callbacks.ModelCheckpoint(filepath='saved_models/weights.best.VGG16.hdf5', 
                               verbose=1, save_best_only=True)

VGG16_model.fit(train_VGG16, train_targets, 
          validation_data=(valid_VGG16, valid_targets),
          epochs=20, batch_size=20, callbacks=[checkpointer], verbose=1)

Epoch 1/20
311/334 [==========================>...] - ETA: 0s - loss: 8.1269 - accuracy: 0.2209
Epoch 1: val_loss improved from inf to 3.37334, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 1s 2ms/step - loss: 7.8087 - accuracy: 0.2347 - val_loss: 3.3733 - val_accuracy: 0.4479
Epoch 2/20
314/334 [===========================>..] - ETA: 0s - loss: 2.1499 - accuracy: 0.5930
Epoch 2: val_loss improved from 3.37334 to 2.27155, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 2.1186 - accuracy: 0.5996 - val_loss: 2.2716 - val_accuracy: 0.6108
Epoch 3/20
322/334 [===========================>..] - ETA: 0s - loss: 1.2170 - accuracy: 0.7410
Epoch 3: val_loss improved from 2.27155 to 2.02929, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 1.2130 - accuracy: 0.7422 - val_loss: 2.0293 - val_accuracy: 0.6575
Epoch 4/20
316/334 [===========================>..] - ETA: 0s - loss: 0.8122 - accuracy: 0.8136
Epoch 4: val_loss improved from 2.02929 to 1.92801, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 0.8118 - accuracy: 0.8135 - val_loss: 1.9280 - val_accuracy: 0.6683
Epoch 5/20
321/334 [===========================>..] - ETA: 0s - loss: 0.5381 - accuracy: 0.8612
Epoch 5: val_loss improved from 1.92801 to 1.92219, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 0.5461 - accuracy: 0.8599 - val_loss: 1.9222 - val_accuracy: 0.6886
Epoch 6/20
319/334 [===========================>..] - ETA: 0s - loss: 0.4038 - accuracy: 0.8937
Epoch 6: val_loss improved from 1.92219 to 1.87971, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 0.4056 - accuracy: 0.8933 - val_loss: 1.8797 - val_accuracy: 0.6826
Epoch 7/20
321/334 [===========================>..] - ETA: 0s - loss: 0.2939 - accuracy: 0.9179
Epoch 7: val_loss improved from 1.87971 to 1.87124, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 0.2939 - accuracy: 0.9180 - val_loss: 1.8712 - val_accuracy: 0.7066
Epoch 8/20
316/334 [===========================>..] - ETA: 0s - loss: 0.2227 - accuracy: 0.9366
Epoch 8: val_loss improved from 1.87124 to 1.85954, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 0.2217 - accuracy: 0.9364 - val_loss: 1.8595 - val_accuracy: 0.7138
Epoch 9/20
300/334 [=========================>....] - ETA: 0s - loss: 0.1709 - accuracy: 0.9482
Epoch 9: val_loss did not improve from 1.85954
334/334 [==============================] - 0s 1ms/step - loss: 0.1706 - accuracy: 0.9484 - val_loss: 1.8749 - val_accuracy: 0.7042
Epoch 10/20
316/334 [===========================>..] - ETA: 0s - loss: 0.1302 - accuracy: 0.9609
Epoch 10: val_loss improved from 1.85954 to 1.80429, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 0.1330 - accuracy: 0.9600 - val_loss: 1.8043 - val_accuracy: 0.7389
Epoch 11/20
320/334 [===========================>..] - ETA: 0s - loss: 0.0987 - accuracy: 0.9697
Epoch 11: val_loss did not improve from 1.80429
334/334 [==============================] - 0s 1ms/step - loss: 0.1029 - accuracy: 0.9692 - val_loss: 1.8370 - val_accuracy: 0.7305
Epoch 12/20
318/334 [===========================>..] - ETA: 0s - loss: 0.0822 - accuracy: 0.9722
Epoch 12: val_loss did not improve from 1.80429
334/334 [==============================] - 0s 1ms/step - loss: 0.0821 - accuracy: 0.9726 - val_loss: 1.8966 - val_accuracy: 0.7210
Epoch 13/20
321/334 [===========================>..] - ETA: 0s - loss: 0.0618 - accuracy: 0.9829
Epoch 13: val_loss did not improve from 1.80429
334/334 [==============================] - 0s 1ms/step - loss: 0.0613 - accuracy: 0.9828 - val_loss: 1.8671 - val_accuracy: 0.7437
Epoch 14/20
319/334 [===========================>..] - ETA: 0s - loss: 0.0535 - accuracy: 0.9828
Epoch 14: val_loss did not improve from 1.80429
334/334 [==============================] - 0s 1ms/step - loss: 0.0554 - accuracy: 0.9825 - val_loss: 1.8186 - val_accuracy: 0.7413
Epoch 15/20
318/334 [===========================>..] - ETA: 0s - loss: 0.0409 - accuracy: 0.9863
Epoch 15: val_loss did not improve from 1.80429
334/334 [==============================] - 0s 1ms/step - loss: 0.0406 - accuracy: 0.9864 - val_loss: 1.8934 - val_accuracy: 0.7497
Epoch 16/20
320/334 [===========================>..] - ETA: 0s - loss: 0.0270 - accuracy: 0.9917
Epoch 16: val_loss did not improve from 1.80429
334/334 [==============================] - 0s 1ms/step - loss: 0.0276 - accuracy: 0.9916 - val_loss: 1.8691 - val_accuracy: 0.7449
Epoch 17/20
316/334 [===========================>..] - ETA: 0s - loss: 0.0264 - accuracy: 0.9922
Epoch 17: val_loss improved from 1.80429 to 1.77331, saving model to saved_models\weights.best.VGG16.hdf5
334/334 [==============================] - 0s 1ms/step - loss: 0.0255 - accuracy: 0.9927 - val_loss: 1.7733 - val_accuracy: 0.7497
Epoch 18/20
314/334 [===========================>..] - ETA: 0s - loss: 0.0271 - accuracy: 0.9904
Epoch 18: val_loss did not improve from 1.77331
334/334 [==============================] - 0s 1ms/step - loss: 0.0266 - accuracy: 0.9906 - val_loss: 1.9998 - val_accuracy: 0.7449
Epoch 19/20
307/334 [==========================>...] - ETA: 0s - loss: 0.0209 - accuracy: 0.9935
Epoch 19: val_loss did not improve from 1.77331
334/334 [==============================] - 0s 1ms/step - loss: 0.0238 - accuracy: 0.9928 - val_loss: 1.9821 - val_accuracy: 0.7461
Epoch 20/20
318/334 [===========================>..] - ETA: 0s - loss: 0.0172 - accuracy: 0.9945
Epoch 20: val_loss did not improve from 1.77331
334/334 [==============================] - 0s 1ms/step - loss: 0.0183 - accuracy: 0.9946 - val_loss: 2.0145 - val_accuracy: 0.7509

<keras.callbacks.History at 0x1ce70b61c90>


VGG16_model.load_weights('saved_models/weights.best.VGG16.hdf5')


# get index of predicted dog breed for each image in test set
VGG16_predictions = [np.argmax(VGG16_model.predict(np.expand_dims(feature, axis=0), verbose=0)) for feature in tqdm(test_VGG16)]

# report test accuracy
test_accuracy = 100*np.sum(np.array(VGG16_predictions)==np.argmax(test_targets, axis=1))/len(VGG16_predictions)
print('Test accuracy: %.4f%%' % test_accuracy)

100%|████████████████████████████████████████████████████████████████████████████████| 836/836 [00:46<00:00, 18.05it/s]

Test accuracy: 73.5646%


from extract_bottleneck_features import *

def VGG16_predict_breed(img_path):
    # extract bottleneck features
    bottleneck_feature = extract_VGG16(path_to_tensor(img_path))
    # obtain predicted vector
    predicted_vector = VGG16_model.predict(bottleneck_feature, verbose=1)
    # return dog breed that is predicted by the model
    return dog_names[np.argmax(predicted_vector)]


for img in dog_files_short[:1] :
    print(img)
    display(Image(img))
    pred = VGG16_predict_breed(img)
    print("Prediction:", pred)

dogImages/train\095.Kuvasz\Kuvasz_06442.jpg

1/1 [==============================] - 0s 192ms/step
1/1 [==============================] - 0s 59ms/step
Prediction: Kuvasz


### TODO: Obtain bottleneck features from another pre-trained CNN.

# These bottleneck files where downloaded separately and stored in bottleneck_features/

# https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogVGG19Data.npz
# https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogResnet50Data.npz
# https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogInceptionV3Data.npz
# https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogXceptionData.npz

# load bottleneck features for all four pretrained networks

networks_pretrained= []

for network in ["VGG19", "ResNet50", "Xception", "InceptionV3"]:
    bnf_path = 'bottleneck_features/Dog{}Data.npz'.format(network)
    print("{:15} loading {} ...".format(network, bnf_path))
    bottleneck_features = np.load(bnf_path)
    d = {
        "network": network,
        "train": bottleneck_features['train'],
        "valid": bottleneck_features['valid'],
        "test": bottleneck_features['test']
    }
    
    networks_pretrained.append(d)

VGG19           loading bottleneck_features/DogVGG19Data.npz ...
ResNet50        loading bottleneck_features/DogResNet50Data.npz ...
Xception        loading bottleneck_features/DogXceptionData.npz ...
InceptionV3     loading bottleneck_features/DogInceptionV3Data.npz ...


# Loop : for each network, add the same basic layers, compile and fit

for n in networks_pretrained :
    name = n["network"]
    model = keras.Sequential(name = name)
    input_shape = n["train"].shape[1:]

    model.add(layers.GlobalAveragePooling2D(input_shape=input_shape))
    model.add(layers.Dense(133, activation='softmax'))
    model.summary()
    
    print("{:15} compiling ...".format(name))
    model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
    
    print("{:15} training model ...".format(name))
    checkpointer = keras.callbacks.ModelCheckpoint(
        filepath='saved_models/weights.best.{}.hdf5'.format(name), 
        verbose=0, 
        save_best_only=True
    )
    
    n["model"] = model
    
    # fit for 30 epochs
    n["hist"] = model.fit(
        n["train"], 
        train_targets, 
        validation_data=(n["valid"], valid_targets),
        epochs=20, 
        batch_size=20, 
        callbacks=[checkpointer], 
        verbose=0)
    
    # print for insight
    plot_loss_acc(n["hist"], n["network"])

Model: "VGG19"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 global_average_pooling2d_3   (None, 512)              0         
 (GlobalAveragePooling2D)                                        
                                                                 
 dense_3 (Dense)             (None, 133)               68229     
                                                                 
=================================================================
Total params: 68,229
Trainable params: 68,229
Non-trainable params: 0
_________________________________________________________________
VGG19           compiling ...
VGG19           training model ...

Model: "ResNet50"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 global_average_pooling2d_4   (None, 2048)             0         
 (GlobalAveragePooling2D)                                        
                                                                 
 dense_4 (Dense)             (None, 133)               272517    
                                                                 
=================================================================
Total params: 272,517
Trainable params: 272,517
Non-trainable params: 0
_________________________________________________________________
ResNet50        compiling ...
ResNet50        training model ...

Model: "Xception"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 global_average_pooling2d_5   (None, 2048)             0         
 (GlobalAveragePooling2D)                                        
                                                                 
 dense_5 (Dense)             (None, 133)               272517    
                                                                 
=================================================================
Total params: 272,517
Trainable params: 272,517
Non-trainable params: 0
_________________________________________________________________
Xception        compiling ...
Xception        training model ...

Model: "InceptionV3"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 global_average_pooling2d_6   (None, 2048)             0         
 (GlobalAveragePooling2D)                                        
                                                                 
 dense_6 (Dense)             (None, 133)               272517    
                                                                 
=================================================================
Total params: 272,517
Trainable params: 272,517
Non-trainable params: 0
_________________________________________________________________
InceptionV3     compiling ...
InceptionV3     training model ...


# Loop : test all predictions and compare

for n in networks_pretrained :
    
    # load best weights from file
    n["model"].load_weights('saved_models/weights.best.{}.hdf5'.format(n["network"]))
    
    print("{:15} Testing ...".format(n["network"]))
    # get index of predicted dog breed for each image in test set
    predictions = [np.argmax(n["model"].predict(np.expand_dims(feature, axis=0), verbose=0)) for feature in tqdm(n["test"])]

    # report test accuracy
    test_accuracy = 100*np.sum(np.array(predictions)==np.argmax(test_targets, axis=1))/len(predictions)
    print(n["network"], 'Test accuracy: %.4f%%' % test_accuracy)

VGG19           Testing ...

100%|████████████████████████████████████████████████████████████████████████████████| 836/836 [00:46<00:00, 18.02it/s]

VGG19 Test accuracy: 72.2488%
ResNet50        Testing ...

100%|████████████████████████████████████████████████████████████████████████████████| 836/836 [00:46<00:00, 17.94it/s]

ResNet50 Test accuracy: 81.1005%
Xception        Testing ...

100%|████████████████████████████████████████████████████████████████████████████████| 836/836 [00:46<00:00, 18.10it/s]

Xception Test accuracy: 84.2105%
InceptionV3     Testing ...

100%|████████████████████████████████████████████████████████████████████████████████| 836/836 [00:46<00:00, 18.07it/s]

InceptionV3 Test accuracy: 79.1866%


### TODO: Define your architecture.

# get bottleneck features from Xception from file
Xception_bottleneck_features = np.load('bottleneck_features/DogXceptionData.npz')
Xception_train = Xception_bottleneck_features['train']
Xception_valid = Xception_bottleneck_features['valid']
Xception_test = Xception_bottleneck_features['test']

# # Configure input and add layers : 
# # Note this one gives acc 84% after 3-4 epochs
model = keras.Sequential(name = "Xception-final")

# add a global spatial average pooling layer.
# add a fully-connected layer designed to distinguish between the 133 breeds.

model.add(layers.GlobalAveragePooling2D(input_shape=Xception_train.shape[1:]))
model.add(layers.Dense(133, activation='softmax'))

# Print summary
model.summary()

Model: "Xception-final"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 global_average_pooling2d_7   (None, 2048)             0         
 (GlobalAveragePooling2D)                                        
                                                                 
 dense_7 (Dense)             (None, 133)               272517    
                                                                 
=================================================================
Total params: 272,517
Trainable params: 272,517
Non-trainable params: 0
_________________________________________________________________


### TODO: Compile the model.
model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
# model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])


# ### TODO: Train the model.
print(model.name)

checkpointer = keras.callbacks.ModelCheckpoint(
    filepath='saved_models/weights.best.{}.hdf5'.format(model.name), 
    verbose=1, 
    save_best_only=True
)

hist = model.fit(
    Xception_train, train_targets, 
    validation_data=(
        Xception_valid, 
        valid_targets),
    epochs=10,
    batch_size=20, 
    callbacks=[checkpointer], 
    verbose=1
)

# plot loss and accuracy 
plot_loss_acc(hist, model.name)

Xception-final
Epoch 1/10
324/334 [============================>.] - ETA: 0s - loss: 1.0726 - accuracy: 0.7341
Epoch 1: val_loss improved from inf to 0.51898, saving model to saved_models\weights.best.Xception-final.hdf5
334/334 [==============================] - 2s 4ms/step - loss: 1.0573 - accuracy: 0.7362 - val_loss: 0.5190 - val_accuracy: 0.8311
Epoch 2/10
319/334 [===========================>..] - ETA: 0s - loss: 0.3997 - accuracy: 0.8730
Epoch 2: val_loss improved from 0.51898 to 0.49622, saving model to saved_models\weights.best.Xception-final.hdf5
334/334 [==============================] - 2s 5ms/step - loss: 0.3974 - accuracy: 0.8738 - val_loss: 0.4962 - val_accuracy: 0.8395
Epoch 3/10
328/334 [============================>.] - ETA: 0s - loss: 0.3205 - accuracy: 0.9026
Epoch 3: val_loss did not improve from 0.49622
334/334 [==============================] - 1s 4ms/step - loss: 0.3200 - accuracy: 0.9028 - val_loss: 0.5127 - val_accuracy: 0.8515
Epoch 4/10
332/334 [============================>.] - ETA: 0s - loss: 0.2737 - accuracy: 0.9102
Epoch 4: val_loss did not improve from 0.49622
334/334 [==============================] - 1s 3ms/step - loss: 0.2754 - accuracy: 0.9103 - val_loss: 0.4980 - val_accuracy: 0.8515
Epoch 5/10
325/334 [============================>.] - ETA: 0s - loss: 0.2482 - accuracy: 0.9248
Epoch 5: val_loss did not improve from 0.49622
334/334 [==============================] - 1s 3ms/step - loss: 0.2447 - accuracy: 0.9256 - val_loss: 0.5360 - val_accuracy: 0.8599
Epoch 6/10
331/334 [============================>.] - ETA: 0s - loss: 0.2228 - accuracy: 0.9310
Epoch 6: val_loss did not improve from 0.49622
334/334 [==============================] - 1s 4ms/step - loss: 0.2218 - accuracy: 0.9311 - val_loss: 0.5474 - val_accuracy: 0.8527
Epoch 7/10
332/334 [============================>.] - ETA: 0s - loss: 0.1918 - accuracy: 0.9410
Epoch 7: val_loss did not improve from 0.49622
334/334 [==============================] - 1s 3ms/step - loss: 0.1926 - accuracy: 0.9407 - val_loss: 0.5479 - val_accuracy: 0.8491
Epoch 8/10
327/334 [============================>.] - ETA: 0s - loss: 0.1775 - accuracy: 0.9465
Epoch 8: val_loss did not improve from 0.49622
334/334 [==============================] - 1s 3ms/step - loss: 0.1764 - accuracy: 0.9469 - val_loss: 0.5572 - val_accuracy: 0.8503
Epoch 9/10
325/334 [============================>.] - ETA: 0s - loss: 0.1563 - accuracy: 0.9517
Epoch 9: val_loss did not improve from 0.49622
334/334 [==============================] - 1s 3ms/step - loss: 0.1564 - accuracy: 0.9513 - val_loss: 0.5495 - val_accuracy: 0.8539
Epoch 10/10
329/334 [============================>.] - ETA: 0s - loss: 0.1436 - accuracy: 0.9555
Epoch 10: val_loss did not improve from 0.49622
334/334 [==============================] - 2s 5ms/step - loss: 0.1432 - accuracy: 0.9555 - val_loss: 0.5717 - val_accuracy: 0.8527


### TODO: Load the model weights with the best validation loss.
model.load_weights('saved_models/weights.best.Xception-final.hdf5')


### TODO: Calculate classification accuracy on the test dataset.

# get index of predicted dog breed for each image in test set
predictions = [np.argmax(model.predict(np.expand_dims(feature, axis=0), verbose=0)) for feature in tqdm(Xception_test)]

# report test accuracy
test_accuracy = 100*np.sum(np.array(predictions)==np.argmax(test_targets, axis=1))/len(predictions)
print(model.name, ' test accuracy: %.4f%%' % test_accuracy)

100%|████████████████████████████████████████████████████████████████████████████████| 836/836 [00:33<00:00, 25.12it/s]

Xception-final  test accuracy: 0.0000%


### TODO: Write a function that takes a path to an image as input
### and returns the dog breed that is predicted by the model.

print(model.name, " predictions...")

def final_model_predict_breed(img_path):
    '''Extract features using built-in keras Xception module 
    Then do the prediction with our model and return dog breed using 
    dog_names labels.'''
    
    # load labels
    dog_names = [item[20:-1] for item in sorted(glob("dogImages/train/*/"))]
    
    # load feature extraction model Xception
    bottleneck_feature = extract_Xception(path_to_tensor(img_path))
    
    # load weights and make predictions
    model.load_weights('saved_models/weights.best.Xception-final.hdf5')
    predicted_vector = model.predict(bottleneck_feature, verbose=0)
    
    return dog_names[np.argmax(predicted_vector)]


# run and show some predictions :)
dog_files_mini = dog_files_short[:10]

preds = [final_model_predict_breed(img) for img in dog_files_mini]
fig_labels = ['file: {}<br>prediction: {}'.format(f.split('\\')[-1],p) for f,p in zip(dog_files_mini, preds)]
gallery(dog_files_mini, fig_labels)

Xception-final  predictions...
1/1 [==============================] - 1s 625ms/step
1/1 [==============================] - 1s 901ms/step
1/1 [==============================] - 1s 636ms/step
1/1 [==============================] - 1s 624ms/step
1/1 [==============================] - 1s 627ms/step
1/1 [==============================] - 1s 627ms/step
1/1 [==============================] - 1s 630ms/step
1/1 [==============================] - 1s 627ms/step
1/1 [==============================] - 1s 638ms/step
1/1 [==============================] - 1s 629ms/step


### TODO: Write your algorithm.
### Feel free to use as many code cells as needed.

def find_human(img_arr, algorithm="dlib-cnn"):
    '''Uses CNN-MMOD algorithm to detect human faces in img_arr.
    Returns face position if a human face is found, otherwise returns False'''
    
    import cv2
    import imutils
    from dlib import cnn_face_detection_model_v1

    if algorithm == "dlib-cnn":
        # more accurate, but slow, this detector is used by default
        # print('using dlib cnn model for human detection...')
        face_cnn = cnn_face_detection_model_v1("mmod/mmod_human_face_detector.dat") 
        rects = face_cnn(img_arr, 1)

        if len(rects) > 0:
            # we are only getting one human face (rects[0])
            face = imutils.face_utils.rect_to_bb(rects[0].rect)
            # face = tuple([int(resize_ratio*x) for x in face])
            confidence = rects[0].confidence
            return face, confidence
        else:
            return None
        
    if algorithm == "hog" :
        # algorithm HoG, this one is faster but has higher error.
        # print('using hog-svm for human detection...')
        gray = gray = cv2.cvtColor(img_arr, cv2.COLOR_BGR2GRAY)
        face_hog = dlib.get_frontal_face_detector()
        rects = face_hog(gray, 1)
        
        if rects : 
            face = imutils.face_utils.rect_to_bb(rects[0])
            confidence = 1.0
            return face, confidence
        
        else:
            return None
    
        
def ResNet50_predict_labels(img_path):
    '''Returns prediction vector for image located at img_path.'''
    
    from keras.applications.resnet import ResNet50 
    from keras.applications.resnet import preprocess_input 
    from keras.applications.resnet import decode_predictions

    img = preprocess_input(path_to_tensor(img_path))
    return np.argmax(ResNet50_model.predict(img, verbose=0))


def find_dog(img_path):
    '''Returns True if a dog is detected in the image stored at img_path.'''
    
    prediction = ResNet50_predict_labels(img_path)
    return ((prediction <= 268) & (prediction >= 151)) 


def find_dogbreed(img_path):
    '''Extract features using built-in keras Xception module 
    Then do the prediction with our model and return dog breed using 
    dog_names labels.'''
    
    # load labels
    dog_names = [item[20:-1] for item in sorted(glob("dogImages/train/*/"))]
    
    # load feature extraction model Xception
    bottleneck_feature = extract_Xception(path_to_tensor(img_path))
    
    # load weights and make predictions
    model.load_weights('saved_models/weights.best.Xception-final.hdf5')
    predicted_vector = model.predict(bottleneck_feature, verbose=0)
    
    return dog_names[np.argmax(predicted_vector)]


def draw_bow(face, img_arr, text, color):
    '''draw boxes using faces coordinates and annotates text in image'''

    x,y,w,h = face
    
    cv2.rectangle(
        img_arr, 
        (x,y), (x+w,y+h), 
        color=color, 
        thickness=2, 
        lineType=cv2.LINE_AA
    )
    cv2.putText(
        img_arr, 
        text, 
        (x,y-3), 
        fontFace=cv2.FONT_HERSHEY_DUPLEX, 
        fontScale=0.7, 
        color=color, 
        lineType=cv2.LINE_AA
    )
    return img_arr


def predict_final(img_path):
    '''Accepts a file path to an image and first determines whether 
    the image contains a human, dog, or neither.
    
    - if a dog is detected, return the predicted breed.
    - if a human is detected, return the resembling dog breed.
    - if neither is detected, provide output that indicates an error.
    '''
    
    import time
    
    print("Analyzing image: {}".format(img_path))
    
    start = time.time()
    
    
    IMG_MAX_WIDTH = 600
    HUMAN_COLOR = (0,0,255)
    
    is_dog = False
    breed = None    #used for both dogs and humans lol
    is_human = False
    human_pos = None  
    
    # import to np array and resize if size is exceeded.
    img_arr = cv2.imread(img_path)
    if img_arr.shape[0] > IMG_MAX_WIDTH:
        img_arr = imutils.resize(img_arr, width=IMG_MAX_WIDTH)
    

    # look for dog and humans
    is_dog = find_dog(img_path)
    
    human_pos = find_human(img_arr, algorithm="hog")
    is_human = human_pos is not None
    
    # predict breed
    
    if is_dog:
        print("Doggo 🐕 found !")
        breed = find_dogbreed(img_path)
        print("Looks like a {}.".format(breed))
        
    elif is_human and not is_dog:
        print("Human 👩👨detected !")
        visual = draw_bow(
            human_pos[0], img_arr, 
            text='human !?', color=HUMAN_COLOR
        )
        breed = find_dogbreed(img_path) 
        print("Anyway, he/she looks like a {}.".format(breed))
        
    elif is_dog and is_human:
        print("❌ Not sure if I see a a dog or a human!, predicting breed anyway !")
        
    else :
        # not human not dog
        print("❌ I wasn't able to find any faces in the picture :'(")
        
        

    # convert BGR image to RGB
    img_arr = cv2.cvtColor(img_arr, cv2.COLOR_BGR2RGB)

    # print("elapsed time : {}".format(time.time() - start))
    
    results = {
        "is_dog" : is_dog,
        "breed" : breed,
        "is_human" : is_human,
        "human_pos" : human_pos,
    }
    
    return (results, img_arr)


## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.

from glob import glob
from pprint import pprint
import matplotlib.image as mpimg

test_images = glob("random_test_images/*/*")

for i in test_images:

    res = predict_final(i)

    pprint(res[0])

    # display the image
    plt.imshow(res[1])
    plt.axis("off")
    plt.show()
    
    # print some images from the training set
    if res[0]["breed"] != None :
        qty = 7
        example_dir = [dir for dir in glob("dogImages/train/*/") if res[0]["breed"] == dir[20:-1]][0]
        fig, ax = plt.subplots(1, qty, figsize=(12, 2))
        fig.suptitle("Other {} examples".format(res[0]['breed']))
        for i, ex in enumerate(glob(example_dir+"/*")[:qty]):
            ax[i].imshow(mpimg.imread(ex))
            ax[i].axis("off")
        plt.show()
    
    print("End\n\n")

Analyzing image: random_test_images\dogs\0002-inmortalidadcangrejo (Small).png
Doggo 🐕 found !
1/1 [==============================] - 1s 860ms/step
Looks like a Icelandic_sheepdog.
{'breed': 'Icelandic_sheepdog',
 'human_pos': None,
 'is_dog': True,
 'is_human': False}

End


Analyzing image: random_test_images\dogs\001.jpeg
Doggo 🐕 found !
1/1 [==============================] - 1s 629ms/step
Looks like a Collie.
{'breed': 'Collie', 'human_pos': None, 'is_dog': True, 'is_human': False}

End


Analyzing image: random_test_images\dogs\1355996702_A-brown-and-white-Boxane-dog.jpg
Doggo 🐕 found !
1/1 [==============================] - 1s 630ms/step
Looks like a Boxer.
{'breed': 'Boxer', 'human_pos': None, 'is_dog': True, 'is_human': False}

End


Analyzing image: random_test_images\dogs\234023992e6c4813861628774eabafd0.jpg
Doggo 🐕 found !
1/1 [==============================] - 1s 629ms/step
Looks like a Neapolitan_mastiff.
{'breed': 'Neapolitan_mastiff',
 'human_pos': None,
 'is_dog': True,
 'is_human': False}

End


Analyzing image: random_test_images\dogs\246145-425x340-schnoodle-dog-cute.jpg
Doggo 🐕 found !
1/1 [==============================] - 1s 635ms/step
Looks like a Miniature_schnauzer.
{'breed': 'Miniature_schnauzer',
 'human_pos': None,
 'is_dog': True,
 'is_human': False}

End


Analyzing image: random_test_images\dogs\5b9eb81a-6e08-4c11-9ded-885e073a975d.jpg
Doggo 🐕 found !
1/1 [==============================] - 1s 626ms/step
Looks like a Norwegian_buhund.
{'breed': 'Norwegian_buhund',
 'human_pos': None,
 'is_dog': True,
 'is_human': False}

End


Analyzing image: random_test_images\dogs\5cd4358d7fc0a.webp
Doggo 🐕 found !
1/1 [==============================] - 1s 629ms/step
Looks like a Chihuahua.
{'breed': 'Chihuahua', 'human_pos': None, 'is_dog': True, 'is_human': False}

End


Analyzing image: random_test_images\dogs\9927eb4c-c9ab-4735-9308-95a108a21d44.jpg
Doggo 🐕 found !
1/1 [==============================] - 1s 908ms/step
Looks like a Canaan_dog.
{'breed': 'Canaan_dog', 'human_pos': None, 'is_dog': True, 'is_human': False}

End


Analyzing image: random_test_images\dogs\american_staff.webp
Doggo 🐕 found !
1/1 [==============================] - 1s 631ms/step
Looks like a American_staffordshire_terrier.
{'breed': 'American_staffordshire_terrier',
 'human_pos': None,
 'is_dog': True,
 'is_human': False}

End


Analyzing image: random_test_images\dogs\black-labrodor-retriever.jpg
Doggo 🐕 found !
1/1 [==============================] - 1s 627ms/step
Looks like a Labrador_retriever.
{'breed': 'Labrador_retriever',
 'human_pos': None,
 'is_dog': True,
 'is_human': False}

Artificial Intelligence Nanodegree¶

Convolutional Neural Networks¶

Project: Write an Algorithm for a Dog Identification App¶

Why We're Here¶

The Road Ahead¶

Step 0: Import Datasets¶

Import Dog Dataset¶

Import Human Dataset¶

Step 1: Detect Humans¶

Write a Human Face Detector¶

(IMPLEMENTATION) Assess the Human Face Detector¶

Step 2: Detect Dogs¶

Pre-process the Data¶

Making Predictions with ResNet-50¶

Write a Dog Detector¶

(IMPLEMENTATION) Assess the Dog Detector¶

Step 3: Create a CNN to Classify Dog Breeds (from Scratch)¶

Pre-process the Data¶

(IMPLEMENTATION) Model Architecture¶

Compile the Model¶

(IMPLEMENTATION) Train the Model¶

Load the Model with the Best Validation Loss¶

Test the Model¶

Step 4: Use a CNN to Classify Dog Breeds¶

Obtain Bottleneck Features¶

Model Architecture¶

Compile the Model¶

Train the Model¶

Load the Model with the Best Validation Loss¶

Test the Model¶

Predict Dog Breed with the Model¶

Step 5: Create a CNN to Classify Dog Breeds (using Transfer Learning)¶

(IMPLEMENTATION) Obtain Bottleneck Features¶

(IMPLEMENTATION) Model Architecture¶

(IMPLEMENTATION) Compile the Model¶

(IMPLEMENTATION) Train the Model¶

(IMPLEMENTATION) Load the Model with the Best Validation Loss¶

(IMPLEMENTATION) Test the Model¶

(IMPLEMENTATION) Predict Dog Breed with the Model¶

Step 6: Write your Algorithm¶

(IMPLEMENTATION) Write your Algorithm¶

Step 7: Test Your Algorithm¶

(IMPLEMENTATION) Test Your Algorithm on Sample Images!¶